No abstract

An algorithm for assigning requests to physical recourses for data centers with independent schedulers for different types of resources (computational resources, network resources, and data stor ages) is considered. This algorithm is based on the combination of greedy and limited search strategies. The algorithm provides a required balance between the computational complexity and quality of assignments by limiting the maximum allowed search depth. Theoretical and experimental results of investigating its features are presented.

No abstract

No abstract

Abstract. In this paper we propose a model of a datacenter that provides an ability to describe a wide class of data center architectures. The resource allocation problem is considered that supports replication of data storage elements. Replication procedure provides a way of congestion elimination on channels connected to data storages with low write rates and high read rates. Experimental investigation that was held with different resource allocation algorithms is showing replication procedure to be able to increase the number of allocated requests.